Thierry Urruty

Detecting eye fixations by projection clustering

The identification of the components of eye movements (fixations and saccades) is an essential part in the analysis of visual behavior because these types of movements provide the basic elements used by further investigations of human vision. However, many of the algorithms that detect fixations present some problems (consistency, robustness, many input parameters). In this article we present a new eye fixation identification technique that is based on clustering of eye positions using projections and projection aggregation.

Toward a higher-level visual representation for content-based image retrieval

Having effective methods to access the desired images is essential nowadays with the availability of a huge amount of digital images. The proposed approach is based on an analogy between content-based image retrieval and text retrieval. The aim of the approach is to build a meaningful mid-level representation of images to be used later on for matching between a query image and other images in the desired database. The approach is based firstly on constructing different visual words using local patch extraction and fusion of descriptors. Secondly, we introduce a new method using multilayer pLSA to eliminate the noisiest words generated by the vocabulary building process. Thirdly, a new spatial weighting scheme is introduced that consists of weighting visual words according to the probability of each visual word to belong to each of the n Gaussian. Finally, we construct visual phrases from groups of visual words that are involved in strong association rules. Experimental results show that our approach outperforms the results of traditional image retrieval techniques.

Spatio-Temporal Optical Flow Analysis for People Counting

In this paper, we present a new approach to count thenumber of people that cross a counting line from monocularvideo images. The proposed approach accumulates imageslices and estimates the optical flow on them. Then, it performsan online blob detection on these slices in order toextract the crossing persons. The number of persons associatedto each blob is determined using a linear regressionmodel applied to blob features which are the position, velocity,orientation and size. The proposed approach is validatedon several datasets captured using either a verticaloverhead or an oblique mounted camera. The real-time performanceand the high counting accuracy of this approachin indoor and outdoor environments are also demonstrated.

Clustering by random projections

Clustering algorithms for multidimensional numerical data must overcome special difficulties due to the irregularities of data distribution. We present a clustering algorithm for numerical data that combines ideas from random projection techniques and density-based clustering. The algorithm consists of two phases: the first phase that entails the use of random projections to detect clusters, and the second phase that consists of certain post-processing techniques of clusters obtained by several random projections. Experiments were performed on synthetic data consisting of randomly-generated points in Rn, synthetic images containing colored regions randomly distributed, and, finally, real images. Our results suggest the potential of our algorithm for image segmentation.

A new spatial weighting scheme for bag-of-visual-words

In this paper, we develop a novel image representation method which is based firstly on constructing visual words based on a local patch extraction and a fusion of descriptors. The spatial constitution of an image is represented with a mixture of n Gaussians in the feature space. The new spatial weighting scheme consists in weighting visual words according to the probability of each visual word belongs to each of the n Gaussians. Experimental results show that the proposed approach integrated to an image retrieval system, outperforms the results of traditional image retrieval techniques.

Simulated evaluation of faceted browsing based on feature selection

In this paper we explore the limitations of facet based browsing which uses sub-needs of an information need for querying and organising the search process in video retrieval. The underlying assumption of this approach is that the search effectiveness will be enhanced if such an approach is employed for interactive video retrieval using textual and visual features. We explore the performance bounds of a faceted system by carrying out a simulated user evaluation on TRECVid data sets, and also on the logs of a prior user experiment with the system. We first present a methodology to reduce the dimensionality of features by selecting the most important ones. Then, we discuss the simulated evaluation strategies employed in our evaluation and the effect on the use of both textual and visual features. Facets created by users are simulated by clustering video shots using textual and visual features. The experimental results of our study demonstrate that the faceted browser can potentially improve the search effectiveness.

KPYR: An Efficient Indexing Method

Motivated by the needs for efficient indexing structures adapted to real applications in video database, we present a new indexing structure named Kpyr. In Kpyr, we use a clustering algorithm to partition the data space into sub-spaces on which we apply Pyramid technique (S. Berchtold, et al., 1998). We thus reduce the search space concerned by a query and improve the performances. We show that our approach provides interesting and performing experimental results for both K-nearest neighbors and window queries

KpyrRec: a recursive multidimensional indexing structure

The emergence of digital technologies in the audio–visual sector requires the use of powerful tools for fast data access. We focus on high multidimensional indexing structures for content-based similarity search in very large audiovisual databases of companies specialized in business films. This paper summarizes our study on analytical and experimental results for two new indexing structures we propose. These structures are integrated and tested in a search tool intended for professional use in large company film databases.

Vector space model adaptation and pseudo relevance feedback for content-based image retrieval

Image retrieval is an important problem for researchers in computer vision and content-based image retrieval (CBIR) fields. Over the last decades, many image retrieval systems were based on image representation as a set of extracted low-level features such as color, texture and shape. Then, systems calculate similarity metrics between features in order to find similar images to a query image. The disadvantage of this approach is that images visually and semantically different may be similar in the low level feature space. So, it is necessary to develop tools to optimize retrieval of information. Integration of vector space models is one solution to improve the performance of image retrieval. In this paper, we present an efficient and effective retrieval framework which includes a vectorization technique combined with a pseudo relevance model. The idea is to transform any similarity matching model (between images) to a vector space model providing a score. A study on several methodologies to obtain the vectorization is presented. Some experiments have been undertaken on Wang, Oxford5k and Inria Holidays datasets to show the performance of our proposed framework.

A semantically significant visual representation for social image retrieval

Having effective methods to access the desired images is essential nowadays with the availability of a huge amount of digital images. We propose a higher-level visual representation that enhances the traditional part-based Bag of Visual Words (BOW) representation in two aspects. Firstly, we introduce a new multilayer semantic significance analysis (MSSA) model to select Semantically Significant Visual Words (SSVWs) from the classical visual words in order to overcome the noisiness of the feature quantization process. Secondly, we strengthen the discrimination power of SSVWs by constructing Semantically Significant Visual Phrases (SSVPs) from frequently co-occurring SSVWs in the same local context that are semantically coherent. Finally, the large-scale extensive experimental results show that the proposed higher-level visual representation outperforms the traditional part-based image representation in social image retrieval.